Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
Last revision Both sides next revision
relational_semantic_network [2018/04/04 18:50]
admin
relational_semantic_network [2018/10/08 12:37]
admin
Line 288: Line 288:
 The framework consists of two core modules: a local module that uses spatial memory to store previous beliefs with parallel updates; and a global graph-reasoning module. Our graph module has three components: a) a knowledge graph where we represent classes as nodes and build edges to encode different types of semantic relationships between them; b) a region graph of the current image where regions in the image are nodes and spatial relationships between these regions are edges; c) an assignment graph that assigns regions to classes. Both the local module and the global module roll-out iteratively and cross-feed predictions to each other to refine estimates. The final predictions are made by combining the best of both modules with an attention mechanism. We show strong performance over plain ConvNets, \eg achieving an 8.4% absolute improvement on ADE measured by per-class average precision. Analysis also shows that the framework is resilient to missing regions for reasoning. The framework consists of two core modules: a local module that uses spatial memory to store previous beliefs with parallel updates; and a global graph-reasoning module. Our graph module has three components: a) a knowledge graph where we represent classes as nodes and build edges to encode different types of semantic relationships between them; b) a region graph of the current image where regions in the image are nodes and spatial relationships between these regions are edges; c) an assignment graph that assigns regions to classes. Both the local module and the global module roll-out iteratively and cross-feed predictions to each other to refine estimates. The final predictions are made by combining the best of both modules with an attention mechanism. We show strong performance over plain ConvNets, \eg achieving an 8.4% absolute improvement on ADE measured by per-class average precision. Analysis also shows that the framework is resilient to missing regions for reasoning.
  
 +https://​arxiv.org/​abs/​1709.07871v2 FiLM: Visual Reasoning with a General Conditioning Layer
 +
 +We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation. FiLM layers influence neural network computation via a simple, feature-wise affine transformation based on conditioning information. We show that FiLM layers are highly effective for visual reasoning - answering image-related questions which require a multi-step, high-level process - a task which has proven difficult for standard deep learning methods that do not explicitly model reasoning. Specifically,​ we show on visual reasoning tasks that FiLM layers 1) halve state-of-the-art error for the CLEVR benchmark, 2) modulate features in a coherent manner, 3) are robust to ablations and architectural modifications,​ and 4) generalize well to challenging,​ new data from few examples or even zero-shot.
 +
 +https://​arxiv.org/​abs/​1803.03067 Compositional Attention Networks for Machine Reasoning
 +
 +We present the MAC network, a novel fully differentiable neural network architecture,​ designed to facilitate explicit and expressive reasoning. MAC moves away from monolithic black-box neural architectures towards a design that encourages both transparency and versatility. The model approaches problems by decomposing them into a series of attention-based reasoning steps, each performed by a novel recurrent Memory, Attention, and Composition (MAC) cell that maintains a separation between control and memory. By stringing the cells together and imposing structural constraints that regulate their interaction,​ MAC effectively learns to perform iterative reasoning processes that are directly inferred from the data in an end-to-end approach. We demonstrate the model'​s strength, robustness and interpretability on the challenging CLEVR dataset for visual reasoning, achieving a new state-of-the-art 98.9% accuracy, halving the error rate of the previous best model. More importantly,​ we show that the model is computationally-efficient and data-efficient,​ in particular requiring 5x less data than existing models to achieve strong results.
 +
 +https://​github.com/​stanfordnlp/​mac-network
 +
 +https://​arxiv.org/​abs/​1805.09354v1 Working Memory Networks: Augmenting Memory Networks with a Relational Reasoning Module
 +
 +https://​arxiv.org/​abs/​1806.01261 ​  ​Relational inductive biases, deep learning, and graph networks
 +
 + We argue that combinatorial generalization must be a top priority for AI to achieve human-like abilities, and that structured representations and computations are key to realizing this objective. ​  We present a new building block for the AI toolkit with a strong relational inductive bias--the graph network--which generalizes and extends various approaches for neural networks that operate on graphs, and provides a straightforward interface for manipulating structured knowledge and producing structured behaviors. We discuss how graph networks can support relational reasoning and combinatorial generalization,​ laying the foundation for more sophisticated,​ interpretable,​ and flexible patterns of reasoning.
 +
 +https://​arxiv.org/​abs/​1807.03877v1 Deep Structured Generative Models
 +
 + In particular, the layout or structure of the scene is encoded by a stochastic and-or graph (sAOG), in which the terminal nodes represent single objects and edges represent relations between objects. ​
 +
 +https://​arxiv.org/​abs/​1807.08204 Towards Neural Theorem Proving at Scale
 +
 + We focus on the Neural Theorem Prover (NTP) model proposed by Rockt{\"​{a}}schel and Riedel (2017), a continuous relaxation of the Prolog backward chaining algorithm where unification between terms is replaced by the similarity between their embedding representations. For answering a given query, this model needs to consider all possible proof paths, and then aggregate results - this quickly becomes infeasible even for small Knowledge Bases (KBs). We observe that we can accurately approximate the inference process in this model by considering only proof paths associated with the highest proof scores. ​
 +
 +https://​arxiv.org/​abs/​1807.08058v1 Learning Heuristics for Automated Reasoning through Deep Reinforcement Learning
 +
 +We demonstrate how to learn efficient heuristics for automated reasoning algorithms through deep reinforcement learning. We consider search algorithms for quantified Boolean logics, that already can solve formulas of impressive size - up to 100s of thousands of variables. The main challenge is to find a representation which lends to making predictions in a scalable way. The heuristics learned through our approach significantly improve over the handwritten heuristics for several sets of formulas.
 +
 +https://​arxiv.org/​abs/​1808.02822v1 ​ Backprop Evolution
 +
 +https://​arxiv.org/​abs/​1808.06068 SeVeN: Augmenting Word Embeddings with Unsupervised Relation Vectors
 +
 +https://​arxiv.org/​abs/​1808.07980 Ontology Reasoning with Deep Neural Networks
 +
 +https://​arxiv.org/​abs/​1808.09333v1 Bridging Knowledge Gaps in Neural Entailment via Symbolic Models
 +
 +We focus on filling these knowledge gaps in the Science Entailment task, by leveraging an external structured knowledge base (KB) of science facts. Our new architecture combines standard neural entailment models with a knowledge lookup module. To facilitate this lookup, we propose a fact-level decomposition of the hypothesis, and verifying the resulting sub-facts against both the textual premise and the structured KB. Our model, NSnet, learns to aggregate predictions from these heterogeneous data formats. ​
 +
 +https://​arxiv.org/​pdf/​1806.01445v2.pdf Embedding Logical Queries on Knowledge Graphs
 +
 +https://​github.com/​williamleif/​graphqembed
 +
 +https://​arxiv.org/​abs/​1806.01822v2 Relational recurrent neural networks
 +
 +We then improve upon these deficits by using a new memory module -- a {Relational Memory Core} (RMC) -- which employs multi-head dot product attention to allow memories to interact. Finally, we test the RMC on a suite of tasks that may profit from more capable relational reasoning across sequential information,​ and show large gains in RL domains (e.g. Mini PacMan), program evaluation, and language modeling, achieving state-of-the-art results on the WikiText-103,​ Project Gutenberg, and GigaWord datasets. https://​github.com/​deepmind/​sonnet/​blob/​master/​sonnet/​python/​modules/​relational_memory.py
 +
 +https://​slideslive.com/​38909774/​embedding-symbolic-computation-within-neural-computation-for-ai-and-nlp
 +
 +https://​arxiv.org/​abs/​1809.11044 Relational Forward Models for Multi-Agent Learning